{"list":"other","total":73,"rows":[{"id":"2103.00020","title":"Learning Transferable Visual Models From Natural Language Supervision","created":"2021-02-26","cited_by_count":33744},{"id":"2005.14165","title":"Language Models are Few-Shot Learners","created":"2020-05-28","cited_by_count":32419},{"id":"1707.06347","title":"Proximal Policy Optimization Algorithms","created":"2017-07-20","cited_by_count":15215},{"id":"1907.11692","title":"RoBERTa: A Robustly Optimized BERT Pretraining Approach","created":"2019-07-26","cited_by_count":13372},{"id":"2201.11903","title":"Chain-of-Thought Prompting Elicits Reasoning in Large Language Models","created":"2022-01-28","cited_by_count":12459},{"id":"2204.02311","title":"PaLM: Scaling Language Modeling with Pathways","created":"2022-04-05","cited_by_count":5326},{"id":"1711.00937","title":"Neural Discrete Representation Learning","created":"2017-11-02","cited_by_count":4712},{"id":"1911.02116","title":"Unsupervised Cross-lingual Representation Learning at Scale","created":"2019-11-05","cited_by_count":3935},{"id":"2303.17651","title":"Self-Refine: Iterative Refinement with Self-Feedback","created":"2023-03-30","cited_by_count":3442},{"id":"1509.02971","title":"Continuous control with deep reinforcement learning","created":"2015-09-09","cited_by_count":3407},{"id":"2305.10601","title":"Tree of Thoughts: Deliberate Problem Solving with Large Language Models","created":"2023-05-17","cited_by_count":3211},{"id":"1502.05477","title":"Trust Region Policy Optimization","created":"2015-02-19","cited_by_count":2580},{"id":"1802.09477","title":"Addressing Function Approximation Error in Actor-Critic Methods","created":"2018-02-26","cited_by_count":2417},{"id":"2305.16291","title":"Voyager: An Open-Ended Embodied Agent with Large Language Models","created":"2023-05-25","cited_by_count":2191},{"id":"1506.02438","title":"High-Dimensional Continuous Control Using Generalized Advantage Estimation","created":"2015-06-08","cited_by_count":2026},{"id":"1606.01540","title":"OpenAI Gym","created":"2016-06-05","cited_by_count":1736},{"id":"1706.02275","title":"Multi-Agent Actor-Critic for Mixed Cooperative-Competitive Environments","created":"2017-06-07","cited_by_count":1558},{"id":"2004.07219","title":"D4RL: Datasets for Deep Data-Driven Reinforcement Learning","created":"2020-04-15","cited_by_count":1427},{"id":"1812.05905","title":"Soft Actor-Critic Algorithms and Applications","created":"2018-12-13","cited_by_count":1240},{"id":"2102.03334","title":"ViLT: Vision-and-Language Transformer Without Convolution or Region Supervision","created":"2021-02-05","cited_by_count":1230},{"id":"1705.05363","title":"Curiosity-driven Exploration by Self-supervised Prediction","created":"2017-05-15","cited_by_count":1194},{"id":"2305.19118","title":"Encouraging Divergent Thinking in Large Language Models through Multi-Agent Debate","created":"2023-05-30","cited_by_count":1011},{"id":"1810.12894","title":"Exploration by Random Network Distillation","created":"2018-10-30","cited_by_count":993},{"id":"2103.01955","title":"The Surprising Effectiveness of PPO in Cooperative, Multi-Agent Games","created":"2021-03-02","cited_by_count":942},{"id":"2109.00859","title":"CodeT5: Identifier-aware Unified Pre-trained Encoder-Decoder Models for Code Understanding and Generation","created":"2021-09-02","cited_by_count":906},{"id":"1709.10087","title":"Learning Complex Dexterous Manipulation with Deep Reinforcement Learning and Demonstrations","created":"2017-09-28","cited_by_count":715},{"id":"1902.04043","title":"The StarCraft Multi-Agent Challenge","created":"2019-02-11","cited_by_count":597},{"id":"2310.04406","title":"Language Agent Tree Search Unifies Reasoning Acting and Planning in Language Models","created":"2023-10-06","cited_by_count":574},{"id":"1806.07011","title":"VirtualHome: Simulating Household Activities via Programs","created":"2018-06-19","cited_by_count":415},{"id":"2302.01560","title":"Describe, Explain, Plan and Select: Interactive Planning with Large Language Models Enables Open-World Multi-Task Agents","created":"2023-02-03","cited_by_count":398},{"id":"1605.07736","title":"Learning Multiagent Communication with Backpropagation","created":"2016-05-25","cited_by_count":366},{"id":"1910.05789","title":"On the Utility of Learning about Humans for Human-AI Coordination","created":"2019-10-13","cited_by_count":349},{"id":"1707.08817","title":"Leveraging Demonstrations for Deep Reinforcement Learning on Robotics Problems with Sparse Rewards","created":"2017-07-27","cited_by_count":319},{"id":"2306.08647","title":"Language to Rewards for Robotic Skill Synthesis","created":"2023-06-14","cited_by_count":312},{"id":"1906.04893","title":"Efficient and Accurate Estimation of Lipschitz Constants for Deep Neural Networks","created":"2019-06-12","cited_by_count":293},{"id":"1904.12901","title":"Challenges of Real-World Reinforcement Learning","created":"2019-04-29","cited_by_count":291},{"id":"2303.00001","title":"Reward Design with Language Models","created":"2023-02-27","cited_by_count":261},{"id":"1802.09464","title":"Multi-Goal Reinforcement Learning: Challenging Robotics Environments and Request for Research","created":"2018-02-26","cited_by_count":260},{"id":"1810.08272","title":"BabyAI: A Platform to Study the Sample Efficiency of Grounded Language Learning","created":"2018-10-18","cited_by_count":244},{"id":"2202.01771","title":"Pre-Trained Language Models for Interactive Decision-Making","created":"2022-02-03","cited_by_count":221},{"id":"1811.05381","title":"Sorting out Lipschitz function approximation","created":"2018-11-13","cited_by_count":213},{"id":"2109.06780","title":"Benchmarking the Spectrum of Agent Capabilities","created":"2021-09-14","cited_by_count":200},{"id":"2302.02662","title":"Grounding Large Language Models in Interactive Environments with Online Reinforcement Learning","created":"2023-02-06","cited_by_count":195},{"id":"1910.07207","title":"Soft Actor-Critic for Discrete Action Settings","created":"2019-10-16","cited_by_count":174},{"id":"2102.06177","title":"Multi-Task Reinforcement Learning with Context-based Representations","created":"2021-02-11","cited_by_count":174},{"id":"2308.00436","title":"SelfCheck: Using LLMs to Zero-Shot Check Their Own Step-by-Step Reasoning","created":"2023-08-01","cited_by_count":159},{"id":"2003.13661","title":"Multi-Task Reinforcement Learning with Soft Modularization","created":"2020-03-30","cited_by_count":143},{"id":"2310.07899","title":"RoboCLIP: One Demonstration is Enough to Learn Robot Policies","created":"2023-10-11","cited_by_count":134},{"id":"1802.04181","title":"State Representation Learning for Control: An Overview","created":"2018-02-12","cited_by_count":127},{"id":"2310.00166","title":"Motif: Intrinsic Motivation from Artificial Intelligence Feedback","created":"2023-09-29","cited_by_count":102},{"id":"1703.10069","title":"Multiagent Bidirectionally-Coordinated Nets: Emergence of Human-level Coordination in Learning to Play StarCraft Combat Games","created":"2017-03-29","cited_by_count":96},{"id":"1804.07193","title":"Lipschitz Continuity in Model-based Reinforcement Learning","created":"2018-04-19","cited_by_count":91},{"id":"1911.01417","title":"Keeping Your Distance: Solving Sparse Reward Tasks Using Self-Balancing Shaped Rewards","created":"2019-11-04","cited_by_count":78},{"id":"2307.14936","title":"PanGu-Coder2: Boosting Large Language Models for Code with Ranking Feedback","created":"2023-07-27","cited_by_count":69},{"id":"2310.10198","title":"MoConVQ: Unified Physics-Based Motion Control via Scalable Discrete Representations","created":"2023-10-16","cited_by_count":60},{"id":"2003.01629","title":"Can Increasing Input Dimensionality Improve Deep Reinforcement Learning?","created":"2020-03-03","cited_by_count":37},{"id":"2309.06687","title":"Self-Refined Large Language Model as Automated Reward Function Designer for Deep Reinforcement Learning in Robotics","created":"2023-09-13","cited_by_count":36},{"id":"2010.14087","title":"Hamilton-Jacobi Deep Q-Learning for Deterministic Continuous-Time Systems with Lipschitz Continuous Controls","created":"2020-10-27","cited_by_count":31},{"id":"2309.11359","title":"Prompt, Plan, Perform: LLM-based Humanoid Control via Quantized Imitation Learning","created":"2023-09-20","cited_by_count":31},{"id":"2306.03604","title":"Enabling Intelligent Interactions between an Agent and an LLM: A Reinforcement Learning Approach","created":"2023-06-06","cited_by_count":28},{"id":"2310.08922","title":"LLaMA Rider: Spurring Large Language Models to Explore the Open World","created":"2023-10-13","cited_by_count":21},{"id":"2308.10088","title":"PACE: Improving Prompt with Actor-Critic Editing for Large Language Model","created":"2023-08-19","cited_by_count":20},{"id":"2311.08935","title":"Supported Trust Region Optimization for Offline Reinforcement Learning","created":"2023-11-15","cited_by_count":20},{"id":"1808.09540","title":"Lipschitz regularized Deep Neural Networks generalize and are adversarially robust","created":"2018-08-28","cited_by_count":19},{"id":"2302.01244","title":"Is Model Ensemble Necessary? Model-based RL via a Single Model with Lipschitz Regularized Value Function","created":"2023-02-02","cited_by_count":19},{"id":"2310.16173","title":"On the Convergence and Sample Complexity Analysis of Deep Q-Networks with $\\epsilon$-Greedy Exploration","created":"2023-10-24","cited_by_count":17},{"id":"2310.09454","title":"LgTS: Dynamic Task Sampling using LLM-generated sub-goals for Reinforcement Learning Agents","created":"2023-10-14","cited_by_count":11},{"id":"2310.00481","title":"LANCAR: Leveraging Language for Context-Aware Robot Locomotion in Unstructured Environments","created":"2023-09-30","cited_by_count":9},{"id":"2309.16347","title":"Intrinsic Language-Guided Exploration for Complex Long-Horizon Robotic Manipulation Tasks","created":"2023-09-28","cited_by_count":8},{"id":"2306.05696","title":"Embodied Executable Policy Learning with Language-based Scene Summarization","created":"2023-06-09","cited_by_count":6},{"id":"1910.01738","title":"State Representation Learning from Demonstration","created":"2019-09-15","cited_by_count":5},{"id":"2308.13542","title":"LaGR-SEQ: Language-Guided Reinforcement Learning with Sample-Efficient Querying","created":"2023-08-21","cited_by_count":5},{"id":"2109.13596","title":"Exploratory State Representation Learning","created":"2021-09-28","cited_by_count":2}],"next_cursor":null}